Browsing by Author "Kongoli, C."

Now showing 1 - 2 of 2

Data Snow Trends in the Illinois State
(Hysen MANKOLLI, 2023) Mankolli, H.; Kongoli, C.; Zucchetti, M.; Dursun, S.
The Chicago area there are in the south-eastern of Lake Michigan in the north of Illinois State with climatic influences from Lake Michigan. The data obtained refer to the stations Chicago, Freeport, Rockford, Kenosha, Aurora, Gary, Joliet, Ottawa, Dixon, Clinton, Dekalb, Kankakee, Pontiac, Peoria, Bloomington. The climate of the Chicago Area is with cold winters and scattered snowfall in the winter months. The study shows some estimates of snowfall trends over a multi-year period. Data refers to reports from the National Oceanic and Atmospheric Administration National Weather Service, Chicago, IL, 333 West University Drive, Romeoville, IL. The analysis of snow precipitation amount data is based on the application of the mathematical method Excel. The results show that precipitation values are different over the years. Trends are given by regression equations. For January 1985-2021: y = 4.4576x + 1937.5, R² = 0.0378. The tendency of the value of snowfall for the months of January is with a constant 4.4576. In the period Seasonal Snowfall Totals for Chicago from 1884 to 2021: y = 2.3353x + 1890.2, R² = 0.0868. The tendency of the value of snowfall for each year period is with a constant 2.3353. The smallest amount of snow precipitation is estimated for the years 1920-1921 with 9.8 inches. The highest amount of snow precipitation is estimated for the years 1978-1979 with 89.7 inch. All result are based on statistical method. Our statewide snowfall records in Illinois start in 1902. There is no long-term trend in snowfall since 1902. However, some decades were snowier than others, such as the 1910s, 1960s, and 1970s. In fact, the 1970s were the snowiest decade on record with an average snowfall of 27.2 inches. Snowfall amounts dropped steeply with less year to year variability for much of the 1980s and into the early 2000s. However, snowfall amounts in the last 6 winters have been more variable with the winter of 2014 being about as snowy as the late 1970s. The snowiest winter on record was 1979 with 44.5 inches. Here are the 5 snowiest winters on record: 1979 with 44.5 inches; 1978 with 44.4 inches; 1912 with 39.5 inches; 2014 with 39.4 inches; 1960 with 38.6 inches; Snowfall is accumulated from July 1 of the first year to June 30 of the second year. The second year is used in the plot and table (for example, 2006 refers to the 2005-2006 season, source: state climatologist Illinois). © 2023, Hysen MANKOLLI. All rights reserved.
Citation - WoS: 19
Citation - Scopus: 26
Short-Term Prediction of Pm2.5 Pollution With Deep Learning Methods
(GLOBAL NETWORK ENVIRONMENTAL SCIENCE & TECHNOLOGY, 2020) Ayturan, Y.A.; Ayturan, Zeynep Cansu; Altun, H.O.; Kongoli, C.; Tuncez, F.D.; Dursun, Şükrü; Öztürk. Ali
Particulate matter (PM), classified according to aerodynamic diameter, is one of the harmful pollutants causing health damaging effects. It is considered as cancerogenic by the World Health Organization (WHO) because of the substances found in the chemical composition of PM. In this study, short-term prediction of PM2.5 pollution at 1, 2 and 3 hours was modelled using deep learning methods. Three deep learning algorithms and the combination thereof were evaluated: Long-short term memory units (LSTM), recurrent neural networks (RNN) and gated recurrent unit (GRU). Air Quality Monitoring Stations of the Ministry of Environment and Urbanization of Turkey were utilized to obtain the data. Specifically, meteorological and air pollution data were obtained from a monitoring station located in Kecioren District of Ankara. Several trials were conducted using different combinations of RNN, GRU and LSTM models. Pollutant concentrations and meteorological factors were integrated into the model as input parameters to predict PM2.5 concentration for 1, 2 and 3 hours. Best results with R-2 of 0.83, 0.7 and 0.63 for 1, 2-, and 3-hour predictions, respectively, were obtained by using a combination of GRU and RNN models. The results of this study are promising for explaining the effect of different deep learning models on prediction performance.